Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0415. Min Range: -1.0415

Max Act: 1.0415. Min Act: -0.0000

Data Index: 539709 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1205729 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9212. Min Act: -0.0000

Data Index: 36097 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9242. Min Act: -0.0000

Data Index: 451 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8938. Min Act: -0.0000

Data Index: 657585 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1094813 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8447. Min Act: -0.0000

Data Index: 489738 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1769189 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1743783 (The Pile)

Max Activating Token Index: 729

Text #9

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8368. Min Act: -0.0000

Data Index: 698098 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7939. Min Act: -0.0000

Data Index: 111837 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1116996 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1178571 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8322. Min Act: -0.0000

Data Index: 338815 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7468. Min Act: -0.0000

Data Index: 525614 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8246. Min Act: -0.0000

Data Index: 28062 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1444180 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1158189 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1139749 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6869. Min Act: -0.0000

Data Index: 236604 (The Pile)

Max Activating Token Index: 937